© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11303
    Prev
    Next
    INDEX
    Explanations

    C++ iostream inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ੰਜ
    1.65
    ख्
    1.60
    তাহ
    1.59
    gef
    1.58
    ries
    1.54
    둰
    1.53
    ্ধে
    1.51
    barui
    1.51
    جاز
    1.50
    ্ধ
    1.50
    POSITIVE LOGITS
    ו
    2.07
    WERS
    2.05
    
    2.05
     Getter
    1.99
    stuffs
    1.94
    TIL
    1.94
    PDO
    1.91
    봇
    1.90
    STRUCTOR
    1.89
     पदार्थ
    1.87
    Activations Density 0.004%

    No Known Activations